arXiv Open Access 2025

Image-based Facial Rig Inversion

Tianxiang Yang Marco Volino Armin Mustafa Greg Maguire Robert Kosk

Lihat Sumber

Abstrak

We present an image-based rig inversion framework that leverages two modalities: RGB appearance and RGB-encoded normal maps. Each modality is processed by an independent Hiera transformer backbone, and the extracted features are fused to regress 102 rig parameters derived from the Facial Action Coding System (FACS). Experiments on synthetic and scanned datasets demonstrate that the method generalizes to scanned data, producing faithful reconstructions.

Topik & Kata Kunci

eess.IV

Penulis (5)

Tianxiang Yang

Marco Volino

Armin Mustafa

Greg Maguire

Robert Kosk

Format Sitasi

APA MLA BibTeX

Yang, T., Volino, M., Mustafa, A., Maguire, G., Kosk, R. (2025). Image-based Facial Rig Inversion. https://arxiv.org/abs/2510.13933

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2025
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓